Cross-Lingual Alignment of Frame Net Annotations through Hidden Markov Models

被引：0
作者：
Annesi, Paolo [1 ]
Basili, Roberto [1 ]
机构：
[1] Univ Roma Tor Vergata, Rome, Italy
来源：
COMPUTATIONAL LINGUISTICS AND INTELLIGENT TEXT PROCESSING | 2010年 / 6008卷
关键词：
D O I：
暂无
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
Resources annotated with frame semantic information support the development of robust systems for shallow semantic parsing. Several researches proposed to automatically transfer the semantic information available for English corpora towards other resource-poor languages. In this paper, a semantic transfer approach is proposed based on Hidden Markov Models applied to aligned corpora. The experimental evaluation reported over an English-Italian corpus is successful, achieving 86% of accuracy on average, and improves on the state of the art methods for the same task.
引用
收藏
页码：12 / 25
页数：14
相关论文
共 14 条
  • [1] [Anonymous], P MT SUMM PHUK THAIL
  • [2] Baker C., 1998, P 36 ANN M ASS COMP, V1, P86, DOI DOI 10.3115/980845.980860
  • [3] Basili R, 2009, LECT NOTES COMPUT SC, V5449, P332, DOI 10.1007/978-3-642-00382-0_27
  • [4] FUNG P, 2004, BIFRAMENET BILINGUAL, P931
  • [5] Hwa R, 2002, 40TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, PROCEEDINGS OF THE CONFERENCE, P392
  • [6] Koehn P., 2007, MOSES OPEN SOURCE TO
  • [7] Och FJ, 2003, COMPUT LINGUIST, V29, pc, DOI 10.1162/089120103321337421
  • [8] PADO S, 2007, P TALN 2007 TOUL FRA
  • [9] PADO S, 2007, THESIS U SAARLANDES
  • [10] Smith D. A., 2004, P EMNLP, P49
12